Presentation 2003/1/28
Content Based Image Retrieval System using Automatic Construction of Feature Space
Kazuki YOKOI, Tetsuya MATSUMOTO, Noboru OHNISHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, the opportunity of the image data handling by the computer has increased by progress of an information society, so the general user also treated a lot of pictures more often. Therefore, image retrieval system which does not depend the use type or image type and can generate a reference key automatically is desired. In this research, the feature vector (the reference features) which serves as a reference key to image data is generated automatically, and our purpose is to develop the image retrieval system which can search similar images using the reverence key. Then, paying attention to the sandglass type neural network and self-organizing map which consider as the method of generating the amount of the reference features automatically, and are known as the technique of information compression, and the three techniques of main-ingredients analysis, it verified about the validity of the amount of the reference features generated using these.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) content based image retrieval / reference features / information reduction / neural network / self-organizing map
Paper # NC2002-132
Date of Issue

Conference Information
Committee NC
Conference Date 2003/1/28(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Content Based Image Retrieval System using Automatic Construction of Feature Space
Sub Title (in English)
Keyword(1) content based image retrieval
Keyword(2) reference features
Keyword(3) information reduction
Keyword(4) neural network
Keyword(5) self-organizing map
1st Author's Name Kazuki YOKOI
1st Author's Affiliation Graduate School of Engineering, Nagoya University()
2nd Author's Name Tetsuya MATSUMOTO
2nd Author's Affiliation Graduate School of Engineering, Nagoya University
3rd Author's Name Noboru OHNISHI
3rd Author's Affiliation Graduate School of Engineering, Nagoya University
Date 2003/1/28
Paper # NC2002-132
Volume (vol) vol.102
Number (no) 628
Page pp.pp.-
#Pages 6
Date of Issue